Illustration of metaphorical builders of chatbots and rag parameter customization

CreateAI Platform Available LLM Models

We are proud to offer 40+ models including multi-modal (voice, image, text) for the ASU community to access securely on the CreateAI Platform. Users can find the following models available for experimentation and use in Model Comparison, ASU GPT, and MyAI Builder (access request required). Updated: March 25, 2025.

Faith Timoh Abang

January 25, 2025

For clarity:

means: “Supported” and “Available” on this platform
means: “Not Available” or “Not Supported” on this platform

ASU GPT has 33 Models Available, Model Comparison has 36 models Available, My AI Builder has 33 models Available

Provider	LLM Name	Modality	API Access	Model Comparison	MyAI Builder	ASU GPT
	Claude 2	Text
	Claude 2.1	Text
	Claude 3 Haiku	Text, Vision
	Claude 3 Opus	Text, Vision
	Claude 3 Sonnet	Text, Vision
	Claude 3.7 Sonnet	Text, Vision
	Claude Instant (Claude v1.2)	Text
	Command	Text
	Command Light	Text
	Jurassic 2 Ultra	Text
	Jurassic 2 Mid	Text
	Llama 3 405B	Text
	Llama 3.2 11B	Text
	Llama 3.2 1B	Text
	Llama 3.2 3B	Text
	Llama 3.2 90B	Text
	Mistral - 7B	Text
	Mixtral - Mistral 8 x 7B	Text
	Mistral Large	Text
	Nova Lite	Text
	Nova Micro	Text
	Nova Pro	Text
	Titan G1 Express	Text
	Titan G1 Light	Text
	Bison (5 variants) - API Only	Text
	Gemini 1.5 Flash	Text, Vision, Audio
	Gemini 2 Flash	Text, Vision, Audio
	Gemini 2 Flash Lite	Text, Vision, Audio
	Gemini 2 Flash Pro	Text, Vision, Audio
	Gemini Pro	Text
	Gemini Pro 1.5	Text, Vision, Audio
	Gemini Pro Vision	Vision
	Imagen3	Image Gen
	Dalle 3	Audio
	GPT 3.5 (2 variants)	Text
	GPT 3.5 (2 variants)	Text
	GPT 4 (3 variants)	Text
	GPT 4 (2 variants)	Text
	GPT 4o	Text
	GPT 4o mini	Text
	GPT 4 Turbo	Text, Vision
	GPT o1	Text
	GPT o1 Mini	Text
	o3 Mini	Text
	OpenAI TTS	Text
	Whisper	Text
	GPT 3.5 (2 variants)	Text
	GPT 4 (2 variants)	Text

Keep Reading

Falling words in various depths of field resembling AI code

Breakdown of RAG Model Parameters, Settings and Their Impact

Kofi Wood

January 1, 2025

Retrieval-Augmented Generation (RAG) is an advanced approach in natural language processing that integrates information retrieval and generative language modeling. Unlike traditional language models that generate responses solely based on their pre-trained knowledge, RAG combines retrieval mechanisms with generative models to enhance the relevance and accuracy of its responses. This hybrid framework works by first retrieving relevant documents or information from a predefined knowledge base (e.g., databases, documents, or PDFs) and then using a generative model (such as a transformer-based model) to synthesize a response that incorporates the retrieved context.